Efficient subtyping of ovarian cancer histopathology whole slide images using active sampling in multiple instance learning

02/17/2023
by   Jack Breen, et al.
0

Weakly-supervised classification of histopathology slides is a computationally intensive task, with a typical whole slide image (WSI) containing billions of pixels to process. We propose Discriminative Region Active Sampling for Multiple Instance Learning (DRAS-MIL), a computationally efficient slide classification method using attention scores to focus sampling on highly discriminative regions. We apply this to the diagnosis of ovarian cancer histological subtypes, which is an essential part of the patient care pathway as different subtypes have different genetic and molecular profiles, treatment options, and patient outcomes. We use a dataset of 714 WSIs acquired from 147 epithelial ovarian cancer patients at Leeds Teaching Hospitals NHS Trust to distinguish the most common subtype, high-grade serous carcinoma, from the other four subtypes (low-grade serous, endometrioid, clear cell, and mucinous carcinomas) combined. We demonstrate that DRAS-MIL can achieve similar classification performance to exhaustive slide analysis, with a 3-fold cross-validated AUC of 0.8679 compared to 0.8781 with standard attention-based MIL classification. Our approach uses at most 18 standard approach, while taking 33 only 14 benefit clinical deployment and the democratisation of AI, reducing the extent to which computational hardware limits end-user adoption.

READ FULL TEXT

page 2

page 4

page 5

page 7

research
04/29/2021

Lung Cancer Diagnosis Using Deep Attention Based on Multiple Instance Learning and Radiomics

Early diagnosis of lung cancer is a key intervention for the treatment o...
research
03/02/2023

Active Learning Enhances Classification of Histopathology Whole Slide Images with Attention-based Multiple Instance Learning

In many histopathology tasks, sample classification depends on morpholog...
research
09/07/2022

Multi-Scale Attention-based Multiple Instance Learning for Classification of Multi-Gigapixel Histology Images

Histology images with multi-gigapixel of resolution yield rich informati...
research
07/27/2023

Weakly Supervised AI for Efficient Analysis of 3D Pathology Samples

Human tissue and its constituent cells form a microenvironment that is f...
research
02/01/2023

Detecting Histologic Glioblastoma Regions of Prognostic Relevance

Glioblastoma is the most common and aggressive malignant adult tumor of ...
research
05/30/2019

An attention-based multi-resolution model for prostate whole slide imageclassification and localization

Histology review is often used as the `gold standard' for disease diagno...
research
02/23/2022

Weakly-supervised learning for image-based classification of primary melanomas into genomic immune subgroups

Determining early-stage prognostic markers and stratifying patients for ...

Please sign up or login with your details

Forgot password? Click here to reset